Cut the chatter. Keep the work. A measured communication policy for coding agents: −32% output tokens, zero lost facts.
#agents-md
68 posts
Silent-executor skill for coding agents. Give it a task, it says "yaparım...", works, says "tamam." Nothing in between — no explanation, no...
让 Agent 的中文回复更直接、清楚,同时保留事实、技术精度与原有语气
Codex agent orchestration skill with adaptive thread thinking, callbacks, QA/review gates, fenced automations, project autopilot, and option...
Fable-model operating discipline for any AI coding agent - Claude Code, Cursor, Copilot, Codex, Gemini, Windsurf, Cline, Amp & more. One npx...
Declarative skill manager for Claude Code and Codex. Declare skills in YAML, pin exact revisions in a lockfile, install them reproducibly in...
Copy-in kit of config-driven agent skills, agents, and CI templates — native to Claude Code and adaptable to any AGENTS.md-reading agent.
Talisman — turn a codebase into a beautiful, brand-styled PDF guide (LaTeX→PDF). An agent skill that works with any coding AI agent. Install...
Local-first context and memory engine for AI-assisted work. Harness-agnostic · Model-agnostic · Privacy-first. Works in Claude, Cursor, Code...
Task-typed prompt-engineering Agent Skills for OpenAI Codex.
基于 UbD 逆向设计的教材写作 skill 组合(支持 Claude Code / Codex CLI):教学定位 → 五件套 gate → 章节树 gate → 逐章写作,例题真算验证、中断...
⚗️ Experimental — A genius-builder brain for your AI coding tools: sharp defaults, real judgment, and the discipline to check their own work...